RSS

Artyom Karpov

Karma: 55

How dan­ger­ous is en­coded rea­son­ing?

Artyom KarpovJun 30, 2025, 11:54 AM
17 points
0 comments10 min readLW link

Philo­soph­i­cal Jailbreaks: Demo of LLM Nihilism

Artyom KarpovJun 4, 2025, 12:03 PM
3 points
0 comments5 min readLW link

The Stegano­graphic Po­ten­tials of Lan­guage Models

May 8, 2025, 11:23 AM
9 points
0 comments1 min readLW link

CCS on com­pound sentences

Artyom KarpovMay 4, 2024, 12:23 PM
6 points
0 comments9 min readLW link

In­duc­ing hu­man-like bi­ases in moral rea­son­ing LMs

Feb 20, 2024, 4:28 PM
23 points
3 comments14 min readLW link

How im­por­tant is AI hack­ing as LLMs ad­vance?

Artyom KarpovJan 29, 2024, 6:41 PM
1 point
0 comments6 min readLW link

My (naive) take on Risks from Learned Optimization

Artyom KarpovOct 31, 2022, 10:59 AM
7 points
0 comments5 min readLW link